Đang chuẩn bị liên kết để tải về tài liệu:
DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring

The novelty of our approach relies on a proper flow and fusion of information (DGHNL structure and its optimization). We show that the proposed DGHNL model with a 29-layer structure is capable to achieve the prediction accuracy of 94.60% (54 errors per 1000 classifications) for the Statlog German credit approval data. |